The present study investigated the reproducibility of cardiovascular responses by presenting a mental task to eight healthy subjects four times at intervals of one year and of several days. Subjects performed a mental subtraction task at the same time of day and under the same conditions. For each experiment day, systolic and diastolic blood pressure (SBP and DBP), mean arterial pressure (MAP), cardiac output (CO), heart rate (HR), stroke volume (SV), and total peripheral resistance (TPR) were measured for a 5-minute baseline period, a 5-minute task period, and a 10-minute recovery period. To examine the reproducibility of cardiovascular response, two-way factorial ANOVA (subject factor and experiment day factor) was conducted, and the intra-class correlation coefficient (ICC) was calculated. The results showed that there were no significant differences between experiment days separated by one year or between those separated by several days for all indexes. The ICCs were high for blood pressures (SBP, DBP and MAP, ICCs>0.8) and cardiac responses (HR, SV, and CO, ICCs>0.7) for both the interval of one year and that of several days. For the total peripheral resistance, ICC was only high at the interval of several days (>0.7). In conclusion, the reproducibility of the blood pressure response to a mental task was proven, and in case of the changed blood pressure, the cardiac responses were also reproduced for intervals of one year and of several days.